{"ID":2845154,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.04008","arxiv_id":"2511.04008","title":"GNN-MoE: Context-Aware Patch Routing using GNNs for Parameter-Efficient Domain Generalization","abstract":"Domain generalization (DG) seeks robust Vision Transformer (ViT) performance on unseen domains. Efficiently adapting pretrained ViTs for DG is challenging; standard fine-tuning is costly and can impair generalization. We propose GNN-MoE, enhancing Parameter-Efficient Fine-Tuning (PEFT) for DG with a Mixture-of-Experts (MoE) framework using efficient Kronecker adapters. Instead of token-based routing, a novel Graph Neural Network (GNN) router (GCN, GAT, SAGE) operates on inter-patch graphs to dynamically assign patches to specialized experts. This context-aware GNN routing leverages inter-patch relationships for better adaptation to domain shifts. GNN-MoE achieves state-of-the-art or competitive DG benchmark performance with high parameter efficiency, highlighting the utility of graph-based contextual routing for robust, lightweight DG.","short_abstract":"Domain generalization (DG) seeks robust Vision Transformer (ViT) performance on unseen domains. Efficiently adapting pretrained ViTs for DG is challenging; standard fine-tuning is costly and can impair generalization. We propose GNN-MoE, enhancing Parameter-Efficient Fine-Tuning (PEFT) for DG with a Mixture-of-Experts...","url_abs":"https://arxiv.org/abs/2511.04008","url_pdf":"https://arxiv.org/pdf/2511.04008v1","authors":"[\"Mahmoud Soliman\",\"Omar Abdelaziz\",\"Ahmed Radwan\",\"Anand\",\"Mohamed Shehata\"]","published":"2025-11-06T03:16:08Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Vision Transformer\",\"Graph Neural Network\",\"Transformer\"]","has_code":false}